KR20190079605A - Method and apparatus for analyzing images of capsule endoscopic based on knowledge model of gastrointestinal tract diseases - Google Patents

Abstract

According to one embodiment of the present invention, provided is a method for analyzing an image of a capsule endoscopic, which comprises the following steps. A capsule endoscopic image analysis device receives signs from a user. The capsule endoscopic image analysis device uses disease information included in a knowledge model to determine a disease in which the signs may appear. The capsule endoscopic image analysis device determines findings which can be seen in a gastrointestinal tract due to the disease by using finding information included in the knowledge model. The capsule endoscopic image analysis device separately provides frames in which the findings appeared in an image photographed by the capsule endoscope.

Description

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a method and apparatus for analyzing a capsule endoscope,

The present invention relates to a method and apparatus for analyzing an image of a capsule endoscope based on a knowledge model. More particularly, the present invention relates to a method for providing clinical information by analyzing images of a capsule endoscope based on a knowledge model defined based on Minimal Standard Terminology for Gastrointestinal Endoscopy (MST) and Capsule Endoscopy Structured Terminology (CEST) .

Capsule endoscopy is a device that is inserted into a human body to observe the gastrointestinal tract and images the body. For the analysis of the capsule endoscopic image, the location of the capsule (esophagus, stomach, plant, It is necessary to confirm information on the information (tumor, polyp, polyp, etc.) found in the location. However, due to the characteristics of the digestive system, when a capsule endoscopy is performed on a patient, 14 to 18 hours of images are obtained. Therefore, it is very time consuming to analyze a large amount of images. Therefore, in order to analyze the capsule endoscopic image, the reader narrows the range of the image to be analyzed on the basis of the suspected disease of the patient and reads it.

Suspected Diseases can be deduced from symptoms prior to performing a capsule endoscopy as an expected disease for major lesions that should be found in a capsule endoscopy image. Once such suspected diseases (or anticipated diseases) are selected, endoscopic features that can be detected from suspected diseases can be identified. For example, a typical finding of Crohn's disease is a dissociated ulcerous lesion that is relatively well-defined between the normal mucosa, which can be analyzed by focusing on the fact that these lesions are discontinuously found.

However, current capsule endoscopy software simply provides image information without consideration of the association between the patient's suspicious disease and the major lesion found in the image. Therefore, there is a growing need for a method for providing clinical information in the image analysis process of capsule endoscopy based on the knowledge model.

The present invention provides a method and apparatus for analyzing an image of a capsule endoscope based on a knowledge model.

The technical problems of the present invention are not limited to the above-mentioned technical problems, and other technical problems which are not mentioned can be clearly understood by those skilled in the art from the following description.

According to another aspect of the present invention, there is provided a method for analyzing a capsule endoscope image, the method comprising: receiving a signature from a user; The capsule endoscopic image analyzing method comprising the steps of: determining a disease (Disease) in which the symptom may appear using disease information included in a knowledge model; The capsule endoscopic image analyzing method comprising the steps of: (a) determining, using the discovery information included in the knowledge model, findings found in the gastrointestinal tract due to the disease; And the capsule endoscopic image analyzing apparatus may separately provide a frame in which the discovery is displayed in an image taken by the capsule endoscope.

Preferably, the capsule endoscopic image analyzing apparatus may further include a step of pre-defining a correlation between the symptom and the disease and a correlation between the disease and the discovery based on the ontology.

Preferably, the step of separately providing the frame further comprises: generating a report conformed to a Capsule Endoscopy Structured Terminology (CEST) by including the frame in the form of an image and including information on the disease and the discovery in the form of text And a step of generating the data.

Preferably, the discovery is plural, and the report further includes statistical information of the discovered number and size of the plurality of discovery.

Preferably, the disease is plural, and the report further includes statistical information of the probability that each disease actually occurs according to the matching rate of each disease belonging to the plurality of diseases to the discovery .

Advantageously, receiving the symptom from the user may further comprise receiving further symptoms from the medical information system.

Preferably, the step of separately providing the frame further includes: displaying a first area providing the entire image captured by the capsule endoscope and a second area displaying only the frame separately in the vicinity of the first area, RTI ID = 0.0 > (GUI). ≪ / RTI >

According to another aspect of the present invention, there is provided an apparatus for analyzing a capsule endoscope image, the apparatus comprising: a symptom input unit for receiving symptoms from a user; A symptom analyzer for determining a disease (Disease) in which the symptom may appear using disease information included in the knowledge model; An image analyzer for determining the findings found in the gastrointestinal tract due to the disease using the discovery information included in the knowledge model; And a disease information output unit for separately providing only the frame in which the discovery is displayed in the image captured by the capsule endoscope.

The effects according to the present invention are as follows.

The present invention proposes a gastrointestinal disease model and analysis system that enables intelligent capsule endoscope software based on knowledge information about suspected diseases. Using the invention proposed in the present invention, it is possible to prevent the symptoms of elevation of leukocytes, anemia, diarrhea, fever, C-reactive protein, , Crohn's disease can be determined on the basis of the gastrointestinal disease model. In order to analyze the image of Crohn's disease, related information is provided to assist the doctor in diagnosis by showing characteristics of longitudinal ulcer, Cobblestone Appearance or Inflammatory Polyposis. do. Through this, it is not just to show the images taken by the capsule endoscope using the viewer program, but to improve the convenience of the medical staff such as the image analyst, the image reader, and the doctor who use the capsule endoscope by providing the clinical information together with the image .

The effects of the present invention are not limited to the effects mentioned above, and other effects not mentioned can be clearly understood to those of ordinary skill in the art from the following description.

1 to 3 are views for explaining an image analysis method of a disease-based capsule endoscope according to an embodiment of the present invention.
Figures 4-7 illustrate the disease model that may be used in an embodiment of the invention in more detail.
FIG. 8 is a view for explaining an image analysis apparatus of a disease model-based capsule endoscope according to an embodiment of the present invention.
9A to 9G are views for explaining a knowledge model used in an embodiment of the present invention.
10 is a flowchart illustrating an image analysis method of a disease-based capsule endoscope according to an embodiment of the present invention.

While the invention is susceptible to various modifications and alternative forms, specific embodiments thereof are shown by way of example in the drawings and will herein be described in detail. It should be understood, however, that the invention is not intended to be limited to the particular embodiments, but includes all modifications, equivalents, and alternatives falling within the spirit and scope of the invention. Like reference numerals are used for like elements in describing each drawing.

The terms first, second, A, B, etc. may be used to describe various elements, but the elements should not be limited by the terms. The terms are used only for the purpose of distinguishing one component from another. For example, without departing from the scope of the present invention, the first component may be referred to as a second component, and similarly, the second component may also be referred to as a first component. And / or < / RTI > includes any combination of a plurality of related listed items or any of a plurality of related listed items.

It is to be understood that when an element is referred to as being "connected" or "connected" to another element, it may be directly connected or connected to the other element, . On the other hand, when an element is referred to as being "directly connected" or "directly connected" to another element, it should be understood that there are no other elements in between.

The terminology used in this application is used only to describe a specific embodiment and is not intended to limit the invention. The singular expressions include plural expressions unless the context clearly dictates otherwise. In the present application, the terms "comprises" or "having" and the like are used to specify that there is a feature, a number, a step, an operation, an element, a component or a combination thereof described in the specification, But do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, or combinations thereof.

Unless defined otherwise, all terms used herein, including technical or scientific terms, have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. Terms such as those defined in commonly used dictionaries are to be interpreted as having a meaning consistent with the contextual meaning of the related art and are to be interpreted as either ideal or overly formal in the sense of the present application Do not.

Hereinafter, preferred embodiments according to the present invention will be described in detail with reference to the accompanying drawings.

1 to 3 are views for explaining an image analysis method of a disease-based capsule endoscope according to an embodiment of the present invention.

Referring to FIG. 1, a disease model used in the present invention is shown at the bottom. In other words, disease models are called knowledge models. Referring to FIG. 1, the disease model used in the present invention is composed of Suspected Diseases and Endoscopic Findings. A suspected disease can be inferred through one or more symptoms. Endoscopic discovery can be inferred through suspected diseases. That is, the next stage of reasoning proceeds through the stages of symptom> suspected disease> endoscopic discovery.

For example, a person using a capsule endoscope can respond to the symptoms currently experienced before the capsule endoscope is inserted into the oral cavity through the cardiopulmonary system. In the example of FIG. 1, when symptoms of elevation of leukocytes, anemia, diarrhea, fever, and reactive protein (C-Reactive Protein) are shown, You can infer Crohn's Diseases. Secondly, the findings that are mainly observed in endoscopic images of patients with Crohn 's disease can be inferred through a pre - learned model. For example, a longitudinal ulcer, a cobblestone appar- ent, and an inflammatory poly- morphism can be inferred, and a capsule endoscopic image of a subject can be provided to the medical staff mainly on the frame in which the findings are photographed. This can provide an indicator of whether a suspected disease, Crohn's disease, has actually occurred.

Referring to the upper part of FIG. 1, a frame of a capsule endoscopic image over 14 hours is shown, and only the frames in which a discovery related to a suspected disease Crohn's disease is found are selected, . In addition, you can generate and provide statistical information about the discovery interval. For example, information such as the number, size, bleeding, and pattern of a longitudinal ulcer can be additionally provided together with image information.

2 is a diagram of a system implementing an image analysis method of a disease-based capsule endoscope proposed in the present invention. Referring to FIG. 2, an endoscopic information system is a system linked to a hospital information system. The endoscopic information system proposed in the present invention interchanges with the hospital information system to exchange medical information. The data received from the hospital information system includes management data (name, age, sex, etc.) for identifying the patient and medical data (history, symptoms, test results, etc.). In addition, data transmitted from the endoscopic information system is information on endoscopic examination results, and includes information about pre-procedure, procedure, and post-procedure.

At this time, the endoscopic information system can manage the knowledge model based on MST and CEST. Minimal Standard Terminology for Gastrointestinal Endoscopy (MST) is the minimum standard definition for gastrointestinal endoscopy established by the International Standard Endoscopy Association and is the terminology standard for endoscopic information systems. Currently, it is recommended to develop an endoscopic information system using these standard terms, and the contents of the contents are not limited to the information about the lesions that can be found from the endoscopic examination, but also the terms of the cause of the test, Is defined.

Capsule Endoscopy Structured Terminology (CEST) is a term standard that focuses not only on endoscopy but also on capsule endoscopy. The proposed standard provides a report specification for preparing the results of capsule endoscopic images. Detailed specifications of the report to be prepared are shown in FIG. 3, and refer to a standard for the text report of the endoscopic information system shown in FIG.

Referring again to FIG. 2, the system receives patient information (Patient Administrative Data) and medical information (Patient Medical Data) through interworking with a hospital information system (HIS), and applies a knowledge model based on the ontology The clinical information about the patient can be recommended and provided. For example, it may recommend a suspected disease based on the patient's symptom information, or recommend a discovery information if there is a suspected disease. Medical staff can provide actual medical services based on this recommended information. In particular, the conventional MST and CEST are for the standard, and only the definition of the term is concerned, but there is a lack of interest in the correlation between them. In order to improve this, the present invention defines an ontology-based knowledge model as a relationship between lesions and a cause (disease, prognostic factor, etc.), and associates a specific item found with an MST or CEST Can be recommended by automatically inferring the data for other items. In particular, since the ontology used in this process is defined based on the terms presented in the MST and CEST standards, the clinical terms that can be suggested or suggested for reasoning are also standard terms. I think it would be better to modify it as an expression of.

Referring to FIG. 3, the endoscopic report shown on the right side of the endoscopic information system of FIG. 2 is shown in more detail. Based on the MST and CEST, the endoscopic report is generated including a text report and images relating to the items shown in Table 1 of FIG. At this time, it is necessary to pay attention to the detected findings shown in Table 1. Findings such as ulcers, hemorrhages, mucosal lesions, and tumors found in the capsule endoscopy images are needed for the report. The disease model-based capsule endoscopy image analysis method proposed in the present invention provides clinical information for automatically searching for such findings based on a knowledge model and generating a report.

That is, by using the method proposed in the present invention, the screening process, which is a process of assisting the reading of the capsule endoscope image and checking whether a discovery related to the suspected disease is actually found in the image taken by the capsule endoscope, is automatically performed, And collect clinical information. This can improve the convenience of the inspector.

Figures 4-7 illustrate the disease model that may be used in an embodiment of the invention in more detail.

Referring to FIG. 4, a process of inputting symptoms and signs by a pre-procedure before the capsule endoscope is inserted into the oral cavity of a testee, and a suspected diagnosis based on the process of receiving a sign and symptoms, . To this end, symptoms and signs and suspected diseases should be pre-established by the ontology.

Referring to the left table of FIG. 4, various symptoms and signs are illustrated from S01 to S11. For example, symptoms such as abdominal pain, vomiting, blood stains, anemia, diarrhea, weight loss, heat, leukocyte increase, C-reactive protein, intestinal blood, and prolonged NSAID use are exemplified. Of these, the symptoms such as S01 to S05 can be inputted into the system in the form of a paper document before the examinee performs the examination using the capsule endoscope. And indications such as S06 to S11 can be entered into the system by the medical staff in charge of the examinee.

Based on the received symptoms and indications, various suspected diseases can be selected, such as D01 to D11 shown in the right table. For example, suspected diseases such as vasodilation, celiac disease, Crohn's disease, hereditary polyp syndrome, lymphoma, non-steroidal antiinflammatory diseases, polyps, tumors, ischemia, stenosis, It is also possible to select a plurality of suspected diseases related to symptoms and signs. Some diseases have similar symptoms or signs.

In this case, when providing a report to the medical staff analyzing the capsule endoscopic image, the ratio of each disease to the finding found in the actual capsule endoscopic image is used to calculate the statistical information Can be generated and provided. The medical staff can diagnose the actual disease and provide medical information to the testee by reflecting the medical findings in such statistical information.

Referring to FIG. 5 below, it can be seen that the correlation between symptoms and signs and suspected diseases is defined by the knowledge model. The correlation shown at the center of FIG. 5 is a part illustrating this correlation. Referring to FIG. 5, in the case of a general test result of the examinee, the contents inputted through the paper interview are received from the medical information system such as EMR, PACS, LIS, and the related suspected diseases are selected. For example, if there is a S10 enema, D01 is selected as a suspected disease. In another example, S01 intestinal bleeding, S04 anemia and S06 weight loss are selected as D02 seli disease. As can be seen from the association of FIG. 5, a combination of multiple symptoms and indications can be used to screen for suspected diseases.

Referring to FIG. 6, it can be seen that the clinical information (Findings) that can be found in the capsule endoscope suggested by the MST is classified. In the conventional MST, only the endoscopic discoveries were defined as a short-stay list form. However, the knowledge model proposed in the present invention is systematized and the association between disease and discovery is defined based on the ontology. When reading a capsule endoscopy, consider discovery information about the suspected disease. MST and CEST have defined the discovery information to be considered when performing endoscopy and have the structure as shown in Fig. However, MST and CEST did not define the discovery information because of the association with disease. Since the defined discovery information is a definition of terms and attributes for all findings that can be found from an endoscope, the association of discovery information on diseases is defined in the present invention as shown in FIG.

For example, in the case of Crohn's disease, the main findings are chronic ulcers, Cobblestone Appearance or Inflammatory Polyposis, non-caseating epitheloid cell granuloma ) Can be observed. Such information is shown in the left table of Fig. The correlation between the symptoms and signs of FIG. 5 and the suspected disease and the correlation between the suspected disease and endoscopic findings of FIG. 7 can be defined using the ontology.

FIG. 8 is a view for explaining an image analysis apparatus of a disease model-based capsule endoscope according to an embodiment of the present invention.

The apparatus for analyzing a disease-based capsule endoscope suggested in the present invention is shown in FIG. 8 as a terminal. A terminal may be in the form of a physical device such as a tablet, smart phone, wearable device, or personal computer. The terminal receives the image captured by the capsule endoscope in real time through a short distance communication with the capsule endoscope image transmitting unit. To this end, the terminal may include a communication unit, and the communication unit of the terminal may include a device communication unit and a server communication unit.

For example, a short-range communication module such as NFC or Bluetooth of a smart phone is used to receive a video captured by a capsule endoscope. Long-distance communication modules such as 3G and LTE can exchange data with the server. The information that the terminal exchanges with the server is information for image analysis. In other words, if the image received from the capsule endoscope is periodically or aperiodically transmitted from the terminal to the server, the server detects the endoscopic discovery based on the gastrointestinal disease knowledge model through the image analysis unit and provides clinical information matching with the suspected disease .

Then, the terminal can receive it through the server communication unit and provide it to the testee or the medical staff through the disease information output interface. In addition, the terminal can receive symptom information from the testee through the symptom information input interface. Although the example shown in FIG. 8 shows a centralized system for analyzing an image on a server based on a knowledge model and receiving only the result in a terminal, the terminal also receives a knowledge model from the server, It can also be implemented as a distributed system for analyzing images. The example of FIG. 8 is only an example for facilitating understanding of the invention, and is not intended to limit the invention.

In more detail, the server may include a symptom analysis unit, an image analysis unit, and a clinical information providing unit. The symptom analyzing unit analyzes the symptoms of the patient inputted from the terminal through the communication unit. The content of the analysis is the inference of the suspected disease according to the symptom, and the information about the suspected suspected disease is transmitted to the terminal again. At this time, the analysis performed is based on the gastrointestinal disease knowledge model. The image analysis unit is a part that receives images and other information taken from the capsule endoscope from a terminal and analyzes it in a server. The analysis is the process of obtaining Luminal Findings from suspect diseases and is based on the GIS knowledge model. The clinical information providing unit provides the clinical information related to the doctor or the reading specialist based on the discovery information obtained from the image analysis unit. The clinical information provided is the attribute information about the lesion that can be found, and it includes the ideal type, number, bleeding, size, etc. of the lesion.

Gastrointestinal disease knowledge model constructed with ontology in database of server includes two kinds of data. The first model is called the first model and the second model is the second model. The first model is the knowledge information about the cause of performing the capsule endoscopy as the disease information. The association between the symptom and the symptom and the disease analyzed before is defined Model. The second model implies the association of suspected diseases with discovery information analyzed on the basis of MST and CEST as discovery information.

The capsule endoscopy image analysis system based on the knowledge model proposed in the present invention shown in FIG. 8 can be used to provide a capsule endoscope with the clinical information necessary for diagnosis through the knowledge model in which relevance to the suspected disease, . This provides intelligent software with convenience and economy by providing clinical information that can assist diagnosis of existing software, which only plays the role of regenerating capsule endoscope image.

9A to 9G are views for explaining a knowledge model used in an embodiment of the present invention.

Referring to FIG. 9A, a knowledge model modeled by an ontology can be confirmed. Here, ontology can be defined as a relational model that expresses the meaning of only objects or relationships with other objects so that a computer can understand an object (object, person, or whatever) like a person.

In particular, if the range of the symptom property is canBeShownBy in the domain of FIG. 9A and the range is Disease, a specific symptom may appear in a specific disease (canBeShownBy) Can be defined. Similarly, if the domain of the Finding property is canBeShownBy and the range is Disease, then it is possible to define a specific finding (canBeShownBy) in a particular disease (Disease). have. In addition, if the range of the Finding property is canBeShownIn and the Range is Anatomy, it is possible to define a specific finding (canBeShownIn) in a specific gastrointestinal (Anatomy) have. Nutrition information and Secretion information can also be constructed using ontologies. This ontology modeling can be expressed in RDF / XML format as shown in FIG. 9B.

Referring to FIG. 9C, a concrete example of the knowledge model constructed by the ontology can be confirmed. Referring to FIG. 9C, the Disease domain can be seen in the tree structure data structure at the top. Hemorrhagic hemorrhage in the disease can be seen by Colitis, Congestive, ForeignBody, Vasculitis, etc. through the property of canBeShownBy. You can also see bleeding from Colon, Stomach, etc. through the canBeShownIn property.

Next, referring to FIG. 9D, another concrete example of the knowledge model constructed by the ontology can be confirmed. Diarrhea, a subtype of MedicalExamination in the Symptom domain, shows diarrhea caused by Crohns disease by the CanBeShownBy attribute. Or diarrhea due to Hereditary Polyposis Syndrome.

Next, referring to FIG. 9E, another concrete example of the knowledge model constructed by the ontology can be confirmed. If we look at CrohnsDisease in the Disease domain, we can confirm that there are CobbleStone, Polyp, and Ulcer in the endoscopic discovery that can be seen in Crohns disease by using hasFindingInfo attribute.

Next, referring to FIG. 9F, the pseudo code of the algorithm for analyzing the capsule endoscope image through symptom-suspected disease-endoscopic discovery using the knowledge model constructed by the ontology can be seen. Referring to FIG. 9F, the checkRelationshipsOfDiseases function receives symptoms as parameters and deduces suspected diseases through the knowledge model. That is, it is a function to inquire disease information which is the first model. Next, the checkRelationshipsOfFindings function receives the suspected disease as a parameter, and deduces the discovery that can be seen in the image captured by the capsule endoscope through the knowledge model.

 By providing a capsule endoscopic frame of a patient having various discovery information similar to the discovery information deduced from the model among the various cases built in the database, it is possible to construct an intelligent system that can assist the diagnosis of the medical staff. Thus, if the capsule endoscopic image is automatically screened and provided, the medical staff can easily review the entire image captured by the capsule endoscope without having to look at it.

Referring to FIG. 9G, a user's screen (GUI) of the image analysis software of the capsule endoscope implemented using the method proposed by the present invention can be confirmed. We can provide only the frames with specific findings from the pre-recorded images, and provide the symptoms and the suspicious disease information together with the images as seen from the left. In addition, the right hemisphere can be provided with an endoscopic discovery found in the imaging of the capsule endoscope due to the suspected disease. This intelligent analysis program can enhance the convenience of the medical staff.

10 is a flowchart illustrating an image analysis method of a disease-based capsule endoscope according to an embodiment of the present invention.

Referring to FIG. 10, a symptom is input from a testee using a capsule endoscope (S1100). In addition to this, the patient can receive the information or signs related to the patient through inputting the symptom through the medical staff or interlocking with the medical information system. Next, diseases related to the symptom information inputted by the examinee are selected using the disease information, which is the first model constituting the knowledge model (S1200), and again, the second model, the discovery information, (S1400). Next, an image in which the findings are found is selected (S1400), and the image is provided to the medical staff through a GUI or the like (S1500).

While the present invention has been described in connection with what is presently considered to be practical exemplary embodiments, it is to be understood that the invention is not limited to the disclosed embodiments, but, on the contrary, You will understand. It is therefore to be understood that the above-described embodiments are illustrative in all aspects and not restrictive.

Claims (5)

Defining a correlation of the capsule endoscopic image analyzing apparatus; defining a correlation between the symptom and the disease and a correlation between the disease and the discovery based on the ontology;
A symptom input unit of the capsule endoscope image analyzing apparatus, receiving symptoms from a user;
The symptom analyzing unit of the capsule endoscope image analyzing apparatus may determine a disease (Disease) in which the symptom may occur by using disease information included in the knowledge model;
An image analyzing unit of the capsule endoscope image analyzing apparatus, using the discovery information included in the knowledge model, to determine the findings found in the gastrointestinal tract due to the disease;
An image analyzing unit of the capsule endoscope image analyzing apparatus generates a text for the discovery information and retrieves an image corresponding to the discovery information from a database; And
The disease information outputting unit of the capsule endoscope image analyzing apparatus may be configured such that when the finding detected in the image captured by the capsule endoscope matches an image retrieved from the database, the finding in the determined disease (Disease) Comparing the detected ratio and separately providing only a frame including text and an image corresponding to the finding,
Wherein the step of pre-defining a correlation between the symptom and the disease is to sort the disease by a relationship comprising the plurality of symptoms. The method according to claim 1,
The step of separately providing the frame further comprises:
Recommending clinical information for generating a report conformed to a Capsule Endoscopy Structured Terminology (CEST) by including the frame in the form of an image and including the disease and the information about the discovery in the form of text,
The discovery is a plurality,
The report further includes statistical information on the probability of each disease occurring according to the number of discoveries, the statistical information on the plurality of discoveries, the matching rate between each disease belonging to the plurality of diseases and the discovery, . ≪ / RTI >
Capsule endoscopic image analysis method. The method according to claim 1,
Wherein the receiving of the symptom from the user comprises:
Comprising the further step of receiving additional Symptoms from the medical information system,
Capsule endoscopic image analysis method. The method according to claim 1,
The step of separately providing the frame further comprises:
Visually providing a first area providing the entire image captured by the capsule endoscope and a second area separately displayed in the vicinity of the first area through a graphical user interface (GUI) ,
Capsule endoscopic image analysis method. A symptom input unit for receiving symptoms from a user;
A symptom analyzer for determining a disease (Disease) in which the symptom may appear using disease information included in the knowledge model;
The method comprising the steps of: determining, by using the discovery information included in the knowledge model, discovery found in the gastrointestinal tract due to the disease; generating a text for the discovery information and retrieving an image corresponding to the discovery information from a database An image analysis unit; And
And a disease information output unit separately providing only a frame including a text and an image corresponding to a detection found in an image captured by the capsule endoscope,
Wherein the disease is selected by a disease involving a plurality of symptoms.

Images